Improved Voxel Coloring Via Volumetric Optimization

Voxel coloring methods reconstruct a three-dimensional volumetric surface model from a set of calibrated twodimensional photographs taken of a scene. In this paper, we recast voxel coloring as an optimization problem, the solution of which strives to minimize reprojection error, which measures how well projections of the reconstructed scene reproduce the photographs. The reprojection error, defined in image space, guides the refinement of the scene reconstruction in object space. Unlike previous voxel coloring methods, ours makes better use of all color information from all viewpoints, and thereby produces higher quality reconstructions. In addition, it allows voxels to be added to, not just removed from, the scene at any time during reconstruction. We examine methods to minimize the reprojection error, including greedy and simulated annealing techniques. Reconstructions of both synthetic and real scenes are presented and analyzed.

[1]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[2]  Thomas Malzbender,et al.  Generalized Voxel Coloring , 1999, Workshop on Vision Algorithms.

[3]  Mark R. Stevens,et al.  Reasoning about object appearance in the context of a scene (computer vision) , 1999 .

[4]  Olivier D. Faugeras,et al.  Complete Dense Stereovision Using Level Set Methods , 1998, ECCV.

[5]  S. Leigh,et al.  Probability and Random Processes for Electrical Engineering , 1989 .

[6]  Pascal Fua,et al.  Reconstructing complex surfaces from multiple stereo views , 1995, Proceedings of IEEE International Conference on Computer Vision.

[7]  Alyn P. Rockwood,et al.  Three-dimensional object reconstruction from two-dimensional images , 1997, Comput. Aided Des..

[8]  Richard Szeliski,et al.  Layered depth images , 1998, SIGGRAPH.

[9]  Paul A. Viola,et al.  Roxels: responsibility weighted 3D volume reconstruction , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.